SUMIN/HuggingFace_transformer
1
0
Fork 0
Code Issues Pull Requests Actions 7 Packages Projects Releases Wiki Activity

[Styling] stylify using ruff (#27144)

Browse Source 
* try to stylify using ruff

* might need to remove these changes?

* use ruf format andruff check

* use isinstance instead of type comparision

* use # fmt: skip

* use # fmt: skip

* nits

* soem styling changes

* update ci job

* nits isinstance

* more files update

* nits

* more nits

* small nits

* check and format

* revert wrong changes

* actually use formatter instead of checker

* nits

* well docbuilder is overwriting this commit

* revert notebook changes

* try to nuke docbuilder

* style

* fix feature exrtaction test

* remve `indent-width = 4`

* fixup

* more nits

* update the ruff version that we use

* style

* nuke docbuilder styling

* leve the print for detected changes

* nits

* Remove file I/O

Co-authored-by: charliermarsh
 <charlie.r.marsh@gmail.com>

* style

* nits

* revert notebook changes

* Add # fmt skip when possible

* Add # fmt skip when possible

* Fix

* More `  # fmt: skip` usage

* More `  # fmt: skip` usage

* More `  # fmt: skip` usage

* NIts

* more fixes

* fix tapas

* Another way to skip

* Recommended way

* Fix two more fiels

* Remove asynch
Remove asynch

---------

Co-authored-by: charliermarsh <charlie.r.marsh@gmail.com>
This commit is contained in:
Arthur
2023-11-16 17:43:19 +01:00
committed by GitHub
parent acb5b4aff5
commit 651408a077
480 changed files with 867 additions and 1059 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
tests/tokenization/test_tokenization_fast.py
View File

@@ -156,9 +156,7 @@ class PreTrainedTokenizationFastTest(TokenizerTesterMixin, unittest.TestCase):
self.assertEqual(tok.pad_token, "<pad>")
self.assertEqual(tok.init_kwargs["max_length"], 512)
self.assertEqual(tok.init_kwargs["pad_to_multiple_of"], 8)
# fmt: off
self.assertEqual(tok(sentences, padding = True), {'input_ids': [[8774, 6, 3, 63, 31, 1748, 55, 1, 0, 0, 0, 0,0, 0, 0, 0],[ 571, 33, 25, 3, 2, 3, 58, 290, 225, 59, 36, 136, 962, 269, 58, 1]], 'token_type_ids': [[0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0],[0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]], 'attention_mask': [[1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0],[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]]})
# fmt: on
self.assertEqual(tok(sentences, padding = True), {'input_ids': [[8774, 6, 3, 63, 31, 1748, 55, 1, 0, 0, 0, 0,0, 0, 0, 0],[ 571, 33, 25, 3, 2, 3, 58, 290, 225, 59, 36, 136, 962, 269, 58, 1]], 'token_type_ids': [[0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0],[0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]], 'attention_mask': [[1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0],[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]]}) # fmt: skip
tokenizer.enable_truncation(8, stride=0, strategy="longest_first", direction="right")
self.assertEqual(
@@ -175,9 +173,7 @@ class PreTrainedTokenizationFastTest(TokenizerTesterMixin, unittest.TestCase):
self.assertEqual(tok.init_kwargs["stride"], 0)
# NOTE even if the model has a default max_length, it is not used...
# thus tok(sentences, truncation = True) does nothing and does not warn either
# fmt: off
self.assertEqual(tok(sentences, truncation = True, max_length = 8), {'input_ids': [[8774, 6, 3, 63, 31, 1748, 55, 1],[ 571, 33, 25, 3, 2, 3, 58, 1]], 'token_type_ids': [[0, 0, 0, 0, 0, 0, 0, 0],[0, 0, 0, 0, 0, 0, 0, 0]], 'attention_mask': [[1, 1, 1, 1, 1, 1, 1, 1],[1, 1, 1, 1, 1, 1, 1, 1]]})
# fmt: on
self.assertEqual(tok(sentences, truncation = True, max_length = 8), {'input_ids': [[8774, 6, 3, 63, 31, 1748, 55, 1],[ 571, 33, 25, 3, 2, 3, 58, 1]], 'token_type_ids': [[0, 0, 0, 0, 0, 0, 0, 0],[0, 0, 0, 0, 0, 0, 0, 0]], 'attention_mask': [[1, 1, 1, 1, 1, 1, 1, 1],[1, 1, 1, 1, 1, 1, 1, 1]]}) # fmt: skip
@require_tokenizers